src/be/nikiroo/fanfix/supported/Fimfiction.java

   1 package be.nikiroo.fanfix.supported;
   2
   3 import java.io.IOException;
   4 import java.io.InputStream;
   5 import java.net.MalformedURLException;
   6 import java.net.URL;
   7 import java.util.AbstractMap;
   8 import java.util.ArrayList;
   9 import java.util.HashMap;
  10 import java.util.List;
  11 import java.util.Map;
  12 import java.util.Map.Entry;
  13 import java.util.Scanner;
  14
  15 import be.nikiroo.fanfix.Instance;
  16 import be.nikiroo.fanfix.data.MetaData;
  17 import be.nikiroo.utils.Image;
  18 import be.nikiroo.utils.Progress;
  19 import be.nikiroo.utils.StringUtils;
  20
  21 /**
  22  * Support class for <a href="http://www.fimfiction.net/">FimFiction.net</a>
  23  * stories, a website dedicated to My Little Pony.
  24  *
  25  * @author niki
  26  */
  27 class Fimfiction extends BasicSupport_Deprecated {
  28         @Override
  29         protected boolean isHtml() {
  30                 return true;
  31         }
  32
  33         @Override
  34         public String getSourceName() {
  35                 return "FimFiction.net";
  36         }
  37
  38         @Override
  39         protected MetaData getMeta(URL source, InputStream in) throws IOException {
  40                 MetaData meta = new MetaData();
  41
  42                 meta.setTitle(getTitle(reset(in)));
  43                 meta.setAuthor(getAuthor(reset(in)));
  44                 meta.setDate(getDate(reset(in)));
  45                 meta.setTags(getTags(reset(in)));
  46                 meta.setSource(getSourceName());
  47                 meta.setUrl(source.toString());
  48                 meta.setPublisher(getSourceName());
  49                 meta.setUuid(source.toString());
  50                 meta.setLuid("");
  51                 meta.setLang("en");
  52                 meta.setSubject("MLP");
  53                 meta.setType(getType().toString());
  54                 meta.setImageDocument(false);
  55                 meta.setCover(getCover(reset(in)));
  56
  57                 return meta;
  58         }
  59
  60         @Override
  61         public Map<String, String> getCookies() {
  62                 Map<String, String> cookies = new HashMap<String, String>();
  63                 cookies.put("view_mature", "true");
  64                 return cookies;
  65         }
  66
  67         private List<String> getTags(InputStream in) {
  68                 List<String> tags = new ArrayList<String>();
  69                 tags.add("MLP");
  70
  71                 @SuppressWarnings("resource")
  72                 Scanner scan = new Scanner(in, "UTF-8");
  73                 scan.useDelimiter("\\n");
  74                 boolean started = false;
  75                 while (scan.hasNext()) {
  76                         String line = scan.next();
  77
  78                         if (!started) {
  79                                 started = line.contains("\"story_container\"");
  80                         }
  81
  82                         if (started && line.contains("class=\"tag-")) {
  83                                 if (line.contains("index.php")) {
  84                                         break; // end of *this story* tags
  85                                 }
  86
  87                                 String keyword = "title=\"";
  88                                 Scanner tagScanner = new Scanner(line);
  89                                 tagScanner.useDelimiter(keyword);
  90                                 if (tagScanner.hasNext()) {
  91                                         tagScanner.next();// Ignore first one
  92                                 }
  93                                 while (tagScanner.hasNext()) {
  94                                         String tag = tagScanner.next();
  95                                         if (tag.contains("\"")) {
  96                                                 tag = tag.split("\"")[0];
  97                                                 tag = StringUtils.unhtml(tag).trim();
  98                                                 if (!tag.isEmpty() && !tags.contains(tag)) {
  99                                                         tags.add(tag);
 100                                                 }
 101                                         }
 102                                 }
 103                                 tagScanner.close();
 104                         }
 105                 }
 106
 107                 return tags;
 108         }
 109
 110         private String getTitle(InputStream in) {
 111                 String line = getLine(in, " property=\"og:title\"", 0);
 112                 if (line != null) {
 113                         int pos = -1;
 114                         for (int i = 0; i < 3; i++) {
 115                                 pos = line.indexOf('"', pos + 1);
 116                         }
 117
 118                         if (pos >= 0) {
 119                                 line = line.substring(pos + 1);
 120                                 pos = line.indexOf('"');
 121                                 if (pos >= 0) {
 122                                         return StringUtils.unhtml(line.substring(0, pos)).trim();
 123                                 }
 124                         }
 125                 }
 126
 127                 return null;
 128         }
 129
 130         private String getAuthor(InputStream in) {
 131                 String line = getLine(in, " href=\"/user/", 0);
 132                 if (line != null) {
 133                         int pos = line.indexOf('"');
 134                         if (pos >= 0) {
 135                                 line = line.substring(pos + 1);
 136                                 pos = line.indexOf('"');
 137                                 if (pos >= 0) {
 138                                         line = line.substring(0, pos);
 139                                         pos = line.lastIndexOf('/');
 140                                         if (pos >= 0) {
 141                                                 line = line.substring(pos + 1);
 142                                                 return line.replace('+', ' ');
 143                                         }
 144                                 }
 145                         }
 146                 }
 147
 148                 return null;
 149         }
 150
 151         private String getDate(InputStream in) {
 152                 String line = getLine(in, "<span class=\"date\">", 0);
 153                 if (line != null) {
 154                         int pos = -1;
 155                         for (int i = 0; i < 3; i++) {
 156                                 pos = line.indexOf('>', pos + 1);
 157                         }
 158
 159                         if (pos >= 0) {
 160                                 line = line.substring(pos + 1);
 161                                 pos = line.indexOf('<');
 162                                 if (pos >= 0) {
 163                                         return line.substring(0, pos).trim();
 164                                 }
 165                         }
 166                 }
 167
 168                 return null;
 169         }
 170
 171         @Override
 172         protected String getDesc(URL source, InputStream in) {
 173                 // the og: meta version is the SHORT resume, this is the LONG resume
 174                 return getLine(in, "class=\"description-text bbcode\"", 1);
 175         }
 176
 177         private Image getCover(InputStream in) {
 178                 // Note: the 'og:image' is the SMALL cover, not the full version
 179                 String cover = getLine(in, "class=\"story_container__story_image\"", 1);
 180                 if (cover != null) {
 181                         int pos = cover.indexOf('"');
 182                         if (pos >= 0) {
 183                                 cover = cover.substring(pos + 1);
 184                                 pos = cover.indexOf('"');
 185                                 if (pos >= 0) {
 186                                         cover = cover.substring(0, pos);
 187                                 }
 188                         }
 189                 }
 190
 191                 return getImage(this, null, cover);
 192         }
 193
 194         @Override
 195         protected List<Entry<String, URL>> getChapters(URL source, InputStream in,
 196                         Progress pg) {
 197                 List<Entry<String, URL>> urls = new ArrayList<Entry<String, URL>>();
 198                 @SuppressWarnings("resource")
 199                 Scanner scan = new Scanner(in, "UTF-8");
 200                 scan.useDelimiter("\\n");
 201                 boolean started = false;
 202                 while (scan.hasNext()) {
 203                         String line = scan.next().trim();
 204
 205                         if (!started) {
 206                                 started = line.equals("<!--Chapters-->");
 207                         } else {
 208                                 if (line.equals("</form>")) {
 209                                         break;
 210                                 }
 211
 212                                 if (line.startsWith("<a href=")
 213                                                 || line.contains("class=\"chapter-title\"")) {
 214                                         // Chapter name
 215                                         String name = line;
 216                                         int pos = name.indexOf('>');
 217                                         if (pos >= 0) {
 218                                                 name = name.substring(pos + 1);
 219                                                 pos = name.indexOf('<');
 220                                                 if (pos >= 0) {
 221                                                         name = name.substring(0, pos);
 222                                                 }
 223                                         }
 224                                         // Chapter content
 225                                         pos = line.indexOf('/');
 226                                         if (pos >= 0) {
 227                                                 line = line.substring(pos); // we take the /, not +1
 228                                                 pos = line.indexOf('"');
 229                                                 if (pos >= 0) {
 230                                                         line = line.substring(0, pos);
 231                                                 }
 232                                         }
 233
 234                                         try {
 235                                                 urls.add(new AbstractMap.SimpleEntry<String, URL>(name,
 236                                                                 new URL("http://www.fimfiction.net" + line)));
 237                                         } catch (MalformedURLException e) {
 238                                                 Instance.getTraceHandler().error(e);
 239                                         }
 240                                 }
 241                         }
 242                 }
 243
 244                 return urls;
 245         }
 246
 247         @Override
 248         protected String getChapterContent(URL source, InputStream in, int number,
 249                         Progress pg) {
 250                 return getLine(in, "<div class=\"bbcode\">", 1);
 251         }
 252
 253         @Override
 254         protected boolean supports(URL url) {
 255                 return "fimfiction.net".equals(url.getHost())
 256                                 || "www.fimfiction.net".equals(url.getHost());
 257         }
 258 }